Instructions to use Abhaykoul/Qwen1.5-0.5B-vortex with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Abhaykoul/Qwen1.5-0.5B-vortex with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Abhaykoul/Qwen1.5-0.5B-vortex")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Abhaykoul/Qwen1.5-0.5B-vortex")
model = AutoModelForCausalLM.from_pretrained("Abhaykoul/Qwen1.5-0.5B-vortex")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Abhaykoul/Qwen1.5-0.5B-vortex with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Abhaykoul/Qwen1.5-0.5B-vortex"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Abhaykoul/Qwen1.5-0.5B-vortex",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Abhaykoul/Qwen1.5-0.5B-vortex

SGLang

How to use Abhaykoul/Qwen1.5-0.5B-vortex with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Abhaykoul/Qwen1.5-0.5B-vortex" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Abhaykoul/Qwen1.5-0.5B-vortex",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Abhaykoul/Qwen1.5-0.5B-vortex" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Abhaykoul/Qwen1.5-0.5B-vortex",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Abhaykoul/Qwen1.5-0.5B-vortex with Docker Model Runner:
```
docker model run hf.co/Abhaykoul/Qwen1.5-0.5B-vortex
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Qwen1.5-0.5B-vortex model card

Qwen1.5-0.5B-vortex is a dealigned chat finetune of the original fantastic Qwen1.5-0.5B model by the Qwen team.

This model was trained on the Vortex mini dataset using axolotl for 5 epoch

Model	Avg	ARC (25-Shot)	HellaSwag (10-Shot)	MMLU (5-Shot)	TruthfulQA (0-shot)	Winogrande (5-shot)	GSM8k (5-shot)
OWenL/Qwen1.5-0.5B	38.62	31.48	49.05	39.35	38.3	57.22	16.3
AbhayKoul/Qwen1.5-0.5B-vortex	38.15	31.74	47.78	38.44	38.92	56.51	15.54
M4-ai/tau-0.5B	36.68	29.27	47.43	37.53	39.39	56.83	9.63
M4-ai/tau-0.5B	36.65	29.01	47.45	37.44	39.39	56.83	9.78
Qwen/Qwen1.5-0.5B-Chat	35.61	30.55	44.07	33.82	42.95	54.62	7.66
M4-ai/tau-0.5B-instruct-DPOR	35.54	28.92	43.63	33.92	42.73	57.06	6.97
sail/SailorOW-0.5B-Chat	33.47	30.38	45.51	26.73	39.85	56.51	1.82
sail/SailorOW-0.5B	33.05	29.69	45.82	25.62	40.76	55.33	1.06
sail/SailorOW-0.5B	33.03	29.69	45.82	25.13	40.74	55.56	1.21

Downloads last month: 92

Safetensors

Model size

0.5B params

Tensor type

BF16

Model tree for Abhaykoul/Qwen1.5-0.5B-vortex

Quantizations

3 models

Abhaykoul
/

Qwen1.5-0.5B-vortex

Qwen1.5-0.5B-vortex model card

Model tree for Abhaykoul/Qwen1.5-0.5B-vortex

Dataset used to train Abhaykoul/Qwen1.5-0.5B-vortex